© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6754
    Prev
    Next
    INDEX
    Explanations

    evaluations related to risk, bias, or assessment

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASS
    -0.78
     ASS
    -0.69
     ass
    -0.68
    bruno
    -0.66
     Assn
    -0.60
     assembly
    -0.60
    =\""
    -0.60
    cipline
    -0.59
     bruno
    -0.59
    ass
    -0.57
    POSITIVE LOGITS
     Assessment
    1.87
     assessment
    1.84
     ASSESSMENT
    1.77
     assessments
    1.73
    Assessment
    1.73
    assessment
    1.66
     Assessments
    1.66
    assess
    1.63
    ASSESSMENT
    1.60
     assessing
    1.59
    Activations Density 0.049%

    No Known Activations